Outcome-verified watchdog for scheduled agents
Watchdog that verifies scheduled agents' artifacts itself — never the claim.
| Endpoint | https://textforagents.com/products/scheduled-agent-outcome-verification/mcp (streamable-http) |
|---|---|
| Registry version | 1.0.0 |
| Now | 8 tools · grade B (85) · pin ts_92f9d6ee15c34696026994712886bd26 · protocol 2024-11-05 |
| First / last listed | 2026-10-27 06:17 UTC / 2026-10-27 06:17 UTC |
| Grade over time | 2026-10-27: B (85), 8 tools |
Is this your server? Own a server? ToolFit hosted watch re-checks it every 24 h ($0.25 per 30 days) or 6 h ($0.60) and sends you an HMAC-signed webhook when its tools or grade change: POST https://api.youraitools.co/toolfit/v1/watch. To opt out, see About & opt-out.
Tools: register_job start_run checkpoint complete_run verify_now watchdog_tick last_verified_success list_verdicts
register_job | Register a scheduled job with an outcome contract (file / URL / record, present + non-empty + fresh, optional hash/marker — or a chain contract whose stages' artifacts are the next stage's required input). Args: job_id, contract, stall_budget_s?, due_in_s?, alert via account webhook. params: job_id*, contract*, stall_budget_s, due_in_s |
start_run | Start a run for a job. Args: job_id. params: job_id* |
checkpoint | Report run progress — the watchdog watches progress checkpoints against the job's own wall-clock budget, never process existence. Args: run_id, note?. params: run_id*, note |
complete_run | Claim completion; the watchdog verifies the declared artifact itself (the claim is never trusted) and issues a signed, hash-chained verdict receipt. Metered check ($0.002 after the one-time 100-check trial / plan rules). Args: run_id, claimed?. params: run_id*, claimed |
verify_now | Spot-verify a job's artifact now (independent fetch/hash/read-back by the watchdog). Metered check ($0.002 after trial / plan rules). Args: job_id. params: job_id* |
watchdog_tick | Run the watchdog sweep: STALLED for active runs with no progress checkpoint inside the job's wall-clock budget, MISSED once per due window with no verified run. Not metered. params: none |
last_verified_success | When was this job's last VERIFIED success, and how old is it? Args: job_id. params: job_id* |
list_verdicts | List this operator's signed verdict receipts + receipt-chain re-verification result. params: none |
Entries describe changes in tool definitions. They are not statements about a server, its quality or its author. The grade measures how the tool definitions fit model providers (token cost, schema compatibility, confusable names) as scored by the ToolFit engine at the time of the listing. JSON: append .json. Opt-out: how or hello@youraitools.co.